License block: Vezha capabilitiesWhat showsCPU per core load in Vezha is passed as cpu.core_pct with label core .This gives visibility not only to the average value, but also to the load profile of each core separately.Why is this important?The average can look acceptable even when one core rests at 100% and limits the performance of the service.A component-by-core section allows you to more accurately diagnose single-threaded limitations, failed pinning, or skew in the scheduler.An example from practiceOn a 16-core node, the overall load was around 35%, but one core was constantly hovering around 95%.After changing the worker settings, the service response stabilized without increasing the number of servers.
CPU per core load
Reading Time: < 1 minute